Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98118
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neur
    -0.08
    ção
    -0.08
     United
    -0.08
     helpers
    -0.08
     shirk
    -0.08
    lıq
    -0.07
     выплаты
    -0.07
    uş
    -0.07
     UAV
    -0.07
    ZT
    -0.07
    POSITIVE LOGITS
    j
    0.08
    brities
    0.08
    ansom
    0.08
     noticing
    0.08
    bers
    0.08
     fail
    0.08
    明
    0.07
    ાર્ટ
    0.07
     nack
    0.07
    fen
    0.07
    Activations Density 0.000%

    No Known Activations